#!/usr/bin/env bash
set -uo pipefail

# CASAN H6 — local-vs-provider telemetry reconciliation (D2).
# Provider-API usage records are the billing ground truth; local metrics must
# not under-report tokens (the cost-hiding attack: trim local metrics so a
# runaway/exfil step looks cheap). Per step, local claimed tokens must cover
# provider-reported tokens within a tolerance; a provider step entirely absent
# from local metrics is also a discrepancy (hidden run).
#
# Usage: telemetry-reconcile.sh <local-metrics.jsonl> <provider-usage.jsonl> [tolerance_pct]
#
# Greppable outputs: TELEMETRY_RECONCILED | TELEMETRY_DISCREPANCY

LOCAL_LOG="${1:-}"
PROVIDER_LOG="${2:-}"
TOLERANCE_PCT="${3:-10}"

if [[ -z "$LOCAL_LOG" || -z "$PROVIDER_LOG" || ! -f "$PROVIDER_LOG" ]]; then
  echo "Usage: telemetry-reconcile.sh <local-metrics.jsonl> <provider-usage.jsonl> [tolerance_pct]" >&2
  exit 64
fi

python - "$LOCAL_LOG" "$PROVIDER_LOG" "$TOLERANCE_PCT" <<'PY'
import json
import sys

local_path, provider_path, tol_pct = sys.argv[1], sys.argv[2], float(sys.argv[3])

def sums_by_step(path):
    totals = {}
    try:
        with open(path, encoding="utf-8") as fh:
            for line in fh:
                line = line.strip()
                if not line:
                    continue
                rec = json.loads(line)
                step = rec.get("step")
                if step is None:
                    continue
                totals[step] = totals.get(step, 0) + int(rec.get("total_tokens", 0))
    except OSError:
        pass
    return totals

local = sums_by_step(local_path)
provider = sums_by_step(provider_path)
if not provider:
    raise SystemExit("TELEMETRY_DISCREPANCY provider log empty — nothing to reconcile against")

issues = []
for step, prov_tokens in sorted(provider.items()):
    loc_tokens = local.get(step)
    if loc_tokens is None:
        issues.append(f"step={step} local=MISSING provider={prov_tokens}")
        continue
    floor = prov_tokens * (1 - tol_pct / 100.0)
    if loc_tokens < floor:
        issues.append(f"step={step} local={loc_tokens} provider={prov_tokens} (under-reported beyond {tol_pct}%)")

if issues:
    for issue in issues:
        print(f"TELEMETRY_DISCREPANCY {issue}", file=sys.stderr)
    raise SystemExit(1)
print(f"TELEMETRY_RECONCILED steps={len(provider)} tolerance_pct={tol_pct}")
PY
exit $?